English
Related papers

Related papers: When Bias Meets Trainability: Connecting Theories …

200 papers

Overparameterised deep neural networks (DNNs) are highly expressive and so can, in principle, generate almost any function that fits a training dataset with zero error. The vast majority of these functions will perform poorly on unseen…

Machine Learning · Computer Science 2021-04-13 Chris Mingard , Guillermo Valle-Pérez , Joar Skalse , Ard A. Louis

Deep Neural Networks (DNNs) excel at many tasks, often rivaling or surpassing human performance. Yet their internal processes remain elusive, frequently described as "black boxes." While performance can be refined experimentally, achieving…

Disordered Systems and Neural Networks · Physics 2025-02-03 Sebastiano Ariosto

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

Machine Learning · Computer Science 2018-02-06 Amir Rosenfeld , John K. Tsotsos

Recurrent and deep neural networks (RNNs/DNNs) are cornerstone architectures in machine learning. Remarkably, RNNs differ from DNNs only by weight sharing, as can be shown through unrolling in time. How does this structural similarity fit…

Machine Learning · Computer Science 2026-02-18 Jan P. Bauer , Kirsten Fischer , Moritz Helias , Agostina Palmigiano

A key property of deep neural networks (DNNs) is their ability to learn new features during training. This intriguing aspect of deep learning stands out most clearly in recently reported Grokking phenomena. While mainly reflected as a…

Machine Learning · Statistics 2024-05-07 Noa Rubin , Inbar Seroussi , Zohar Ringel

Training vision transformer networks on small datasets poses challenges. In contrast, convolutional neural networks (CNNs) can achieve state-of-the-art performance by leveraging their architectural inductive bias. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Jianqiao Zheng , Xueqian Li , Simon Lucey

The key distinguishing property of a Bayesian approach is marginalization instead of optimization, not the prior, or Bayes rule. Bayesian inference is especially compelling for deep neural networks. (1) Neural networks are typically…

Machine Learning · Computer Science 2020-01-30 Andrew Gordon Wilson

Research aimed at scaling up neuroscience inspired learning algorithms for neural networks is accelerating. Recently, a key research area has been the study of energy-based learning algorithms such as predictive coding, due to their…

Machine Learning · Computer Science 2026-01-30 Luca Pinchetti , Simon Frieder , Thomas Lukasiewicz , Tommaso Salvatori

Many deep neural networks trained on natural images exhibit a curious phenomenon in common: on the first layer they learn features similar to Gabor filters and color blobs. Such first-layer features appear not to be specific to a particular…

Machine Learning · Computer Science 2014-12-09 Jason Yosinski , Jeff Clune , Yoshua Bengio , Hod Lipson

Graph Neural Networks (GNNs) have emerged as the leading paradigm for solving graph analytical problems in various real-world applications. Nevertheless, GNNs could potentially render biased predictions towards certain demographic…

Machine Learning · Computer Science 2022-11-29 Yushun Dong , Song Wang , Jing Ma , Ninghao Liu , Jundong Li

In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework…

Machine Learning · Computer Science 2018-11-09 Shengjia Zhao , Hongyu Ren , Arianna Yuan , Jiaming Song , Noah Goodman , Stefano Ermon

Graph neural networks (GNNs) are effective models for representation learning on relational data. However, standard GNNs are limited in their expressive power, as they cannot distinguish graphs beyond the capability of the Weisfeiler-Leman…

Machine Learning · Computer Science 2021-06-07 Ralph Abboud , İsmail İlkan Ceylan , Martin Grohe , Thomas Lukasiewicz

Convolutional Neural Networks spread through computer vision like a wildfire, impacting almost all visual tasks imaginable. Despite this, few researchers dare to train their models from scratch. Most work builds on one of a handful of…

Computer Vision and Pattern Recognition · Computer Science 2016-09-26 Philipp Krähenbühl , Carl Doersch , Jeff Donahue , Trevor Darrell

Graph neural networks (GNNs) have become the standard tool for encoding data and their complex relationships into continuous representations, improving prediction accuracy in several machine learning tasks like node classification and link…

Machine Learning · Computer Science 2026-01-27 Megha Khosla

Understanding how the brain learns can be advanced by investigating biologically plausible learning rules -- those that obey known biological constraints, such as locality, to serve as valid brain learning models. Yet, many studies overlook…

Neural and Evolutionary Computing · Computer Science 2025-01-13 Weixuan Liu , Xinyue Zhang , Yuhan Helena Liu

Voltage prediction in distribution grids is a critical yet difficult task for maintaining power system stability. Machine learning approaches, particularly Graph Neural Networks (GNNs), offer significant speedups but suffer from poor…

Machine Learning · Computer Science 2025-12-09 Ehimare Okoyomon , Arbel Yaniv , Christoph Goebel

Even though dense networks have lost importance today, they are still used as final logic elements. It could be shown that these dense networks can be simplified by the sparse graph interpretation. This in turn shows that the information…

Neural and Evolutionary Computing · Computer Science 2018-09-25 Thomas Pircher , Dominik Haspel , Eberhard Schlücker

Background. A main theoretical puzzle is why over-parameterized Neural Networks (NNs) generalize well when trained to zero loss (i.e., so they interpolate the data). Usually, the NN is trained with Stochastic Gradient Descent (SGD) or one…

Machine Learning · Computer Science 2025-02-18 Gon Buzaglo , Itamar Harel , Mor Shpigel Nacson , Alon Brutzkus , Nathan Srebro , Daniel Soudry

While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood. In this work, we study the case of binary classification and prove various…

Machine Learning · Computer Science 2020-12-15 Remi Tachet , Mohammad Pezeshki , Samira Shabanian , Aaron Courville , Yoshua Bengio

Normalization layers were introduced to stabilize and accelerate training, yet their influence is critical already at initialization, where they shape signal propagation and output statistics before parameters adapt to data. In practice,…

Machine Learning · Computer Science 2026-04-03 Emanuele Francazi , Francesco Pinto , Aurelien Lucchi , Marco Baity-Jesi